Coding Model Ranking

AI BENCHY Category

See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↑.

Models Shown

Average Coding Score

5.7

Best Model

Failure Reasons

With failure reason Wrong answer230 With failure reason API error43 With failure reason Timed out23 With failure reason No answer18 With failure reason Did not follow instructions16 With failure reason Extra formatting12

188/188

Rank	Model	Company	Coding Score	Score	Total Cost	Tests Correct	Response Time (avg)
#38	Claude Sonnet 4.6 medium	Anthropic	5.7	7.8	$1.418	1/3	33.3s
Total Tests 3 Wrong Tests 2 Total Cost $1.418 Response Time (avg) 33.3s
#26	Grok 4.5 medium	X AI	7.6	8.3	$1.696	2/3	155.7s
Total Tests 3 Wrong Tests 1 Total Cost $1.696 Response Time (avg) 155.7s
#96	Gemini 3.1 Flash Lite high	Google	3.3	6.5	$2.044	1/1	137.6s
Total Tests 1 Wrong Tests 0 Total Cost $2.044 Response Time (avg) 137.6s
#48	Claude Opus 4.6 medium	Anthropic	5.7	7.7	$2.053	1/3	30.1s
Total Tests 3 Wrong Tests 2 Total Cost $2.053 Response Time (avg) 30.1s
#110	Gemini 3.1 Flash Lite Preview high	Google	0.0	6.1	$2.310	0/0	0ms
Total Tests 0 Wrong Tests 0 Total Cost $2.310 Response Time (avg) 0ms
#9	Claude Fable 5 medium	Anthropic	10.0	9.2	$3.165	3/3	15.6s
Total Tests 3 Wrong Tests 0 Total Cost $3.165 Response Time (avg) 15.6s
#12	GPT-5.5 medium	OpenAI	8.8	9.0	$3.679	2/3	59.8s
Total Tests 3 Wrong Tests 1 Total Cost $3.679 Response Time (avg) 59.8s
#155	Grok 4.20 Multi Agent Beta medium	X AI	3.3	5.0	$5.599	1/1	27.1s
Total Tests 1 Wrong Tests 0 Total Cost $5.599 Response Time (avg) 27.1s

Coding Ranking